A New Reward Function for Bayesian Feasibility Determination.
Junying HeSeong-Hee KimPublished in: WSC (2019)
Keyphrases
- reward function
- reinforcement learning
- markov decision processes
- inverse reinforcement learning
- reinforcement learning algorithms
- state space
- optimal policy
- hierarchical reinforcement learning
- multiple agents
- bayesian inference
- transition model
- maximum likelihood
- state variables
- initially unknown
- transition probabilities
- function approximation
- random walk
- bayesian networks